MAE

Search everything

Mentions · 7d0
Mentions · 30d1
All mentions1
First seenSep 29, 2026
Last mentioned26d ago

Timeline

1 articles · newest first

I Have a Stream: Making Self-Supervised Learning Work on Continuous Video

StreamMAE adapts masked autoencoders so pretraining works on continuous video streams without global shuffling.

Hugging Face daily papersSep 29, 20:00 UTC · 26d agoAI research2

Appears with

ImageNetproduct · 1
StreamMAEai model · 1

Entities are extracted by the model from each article. First seen Sep 29, 2026, last mentioned 26d ago. Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.